Use cases
The agent actions that need a decision before they run
Each use case starts from a rule your business already applies to human staff: a refund limit, a discount ceiling, an outreach rule, a deletion restriction. Gatewise applies the same rule to agents.
agent-fleet / production- 01Refund
money - 02Discount
margin - 03CRM change
records - 04Outbound
customer
- 01
AI agent refund controls
Control autonomous refunds using transaction state, customer data and monetary thresholds. Gatewise decides whether a refund may be issued before the payment tool is called.
ALLOWREQUIRE APPROVALBLOCKINSUFFICIENT EVIDENCE - 02
AI sales discount controls
Enforce discount limits and route exceptions for approval. Gatewise checks deal size, margin rules and prior concessions before a discount is applied.
ALLOWBLOCKREQUIRE APPROVAL - 03
AI customer communication controls
Prevent duplicate, inappropriate or unauthorized customer outreach. Gatewise checks contact state, consent and recent history before a message leaves your systems.
ALLOWNO ACTIONBLOCK - 04
AI CRM action controls
Control record updates, ownership changes, lifecycle changes and destructive actions. Gatewise separates safe enrichment from changes that move revenue data.
ALLOWREQUIRE APPROVALBLOCK - 05
AI contract and renewal controls
Verify timing, ownership and business rules before renewal related actions are executed. Contract terms are precise, so the controls around them should be too.
ALLOWBLOCKNO ACTION - 06
AI finance workflow controls
Apply deterministic evidence and approval rules before financially sensitive actions. Payouts, credits and write-offs get the same treatment as human initiated finance work.
ALLOWREQUIRE APPROVALBLOCK
Concepts
Understand the category
- AI agent authorizationGive agents the authority they need, with a clear decision before every consequential action.
- MCP security for agent tool callsProtect the connection.
- AI agent action controlAction control is the layer that decides whether a proposed agent action may execute.
- AI agent guardrailsMost guardrails work on text.
- AI agent governanceGovernance only counts when it changes what happens.
- AI agent policy engineBusiness rules should not depend on an LLM remembering them.
- AI agent approval workflowsAutonomy is a range, not a switch.
- AI agent audit trailKnow what your agent requested, which rule applied and why the decision was made.
Give your agents freedom without giving them a blank cheque.
Tell us what your agents are allowed to do today. We will review whether Gatewise fits your agent workflow.
Works with your agents and existing business tools